Llama 4 Maverick
Meta developed Llama 4 Maverick as a multimodal language model capable of processing both text and image inputs. It utilizes a mixture-of-experts architecture to handle complex tasks with an extensive 524,288 token context window. The model supports tool calling for integrated workflows.
Llama 4 Maverick specs and pricing
- Provider: Meta
- Released: April 5, 2025
- Context window: 524K tokens
- Max output: 33K tokens
- Input: text, images
- Output: text
- Price: $0.35 input / $1.00 output per 1M tokens
- Tool calling: yes
What Llama 4 Maverick is good at
- Analyzing large documents and image-based data
- Complex tasks requiring external tool integration
- High-volume text processing and reasoning
To-dos to try with Llama 4 Maverick
- Analyze a set of 50 technical diagrams and summarize the common design flaws found in all of them.
- Read a 400-page research report and extract all mentioned methodology steps into a structured table.
- Use a search tool to find current industry trends and synthesize them into a short briefing document.
FAQ
- What types of data can Llama 4 Maverick process? The model is multimodal and can accept both text and image files as input.
- Does this model support external tools? Yes, Llama 4 Maverick is designed with tool-calling capabilities to assist in executing specific tasks.
- How much does Llama 4 Maverick cost? Llama 4 Maverick costs $0.35 per million input tokens and $1.00 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 1.12 credits ($1 = 100 credits).
- What is the context window of Llama 4 Maverick? Llama 4 Maverick can read up to 524K tokens at once and write up to 33K tokens in one reply.
- Can I use Llama 4 Maverick without coding? Yes. In todo.is you pick Llama 4 Maverick as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.